Image-Text-to-Text
PaddleOCR
Safetensors
English
Chinese
multilingual
paddleocr_vl
ERNIE4.5
PaddlePaddle
image-to-text
ocr
document-parse
layout
table
formula
chart
conversational
custom_code
Eval Results
Instructions to use PaddlePaddle/PaddleOCR-VL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PaddleOCR
How to use PaddlePaddle/PaddleOCR-VL with PaddleOCR:
# See https://www.paddleocr.ai/latest/version3.x/pipeline_usage/PaddleOCR-VL.html to installation from paddleocr import PaddleOCRVL pipeline = PaddleOCRVL(pipeline_version="v1") output = pipeline.predict("path/to/document_image.png") for res in output: res.print() res.save_to_json(save_path="output") res.save_to_markdown(save_path="output") - Notebooks
- Google Colab
- Kaggle
how to output a table with ocr as a table
#58
by maaldic - opened
Hello,
I would like to take tables from a pdf with ocr just like you guys did in the demo here: https://aistudio.baidu.com/paddleocr
How can I get such an output with PaddlePaddle/PaddleOCR-VL? I managed to run this model on Kaggle with GPU, and also managed to take a table as JSON
maaldic changed discussion title from how to output table as a table with ocr to how to output a table with ocr as a table
I'm having the same issue, cannot get the table. it only gets flat text. my prompt is OCR: